Sammanfattning
| Originalspråk | engelska |
|---|---|
| Tidskrift | Journal of Systems Architecture |
| Volym | 93 |
| Sidor (från-till) | 1-19 |
| Antal sidor | 19 |
| ISSN | 1383-7621 |
| DOI | |
| Status | Publicerad - feb 2019 |
| MoE-publikationstyp | A1 Tidskriftsartikel-refererad |
Vetenskapsgrenar
- 113 Data- och informationsvetenskap
Citera det här
}
An Integrated Hardware/Software Design Methodology for Signal Processing Systems. / Li, Lin; Sau, Carlo; Fanni, Tiziana; Li, Jingui; Viitanen, Timo ; Christophe, Francois; Palumbo, Francesca; Raffo, Luigi; Huttunen, Heikki; Takala, Jarmo; Bhattacharyya, Shuvra S.
I: Journal of Systems Architecture, Vol. 93, 02.2019, s. 1-19.Forskningsoutput: Tidskriftsbidrag › Artikel › Vetenskaplig › Peer review
TY - JOUR
T1 - An Integrated Hardware/Software Design Methodology for Signal Processing Systems
AU - Li, Lin
AU - Sau, Carlo
AU - Fanni, Tiziana
AU - Li, Jingui
AU - Viitanen, Timo
AU - Christophe, Francois
AU - Palumbo, Francesca
AU - Raffo, Luigi
AU - Huttunen, Heikki
AU - Takala, Jarmo
AU - Bhattacharyya, Shuvra S.
PY - 2019/2
Y1 - 2019/2
N2 - This paper presents a new methodology for design and implementation of signal processing systems on system-on-chip (SoC) platforms. The methodology is centered on the use of lightweight application programming interfaces for applying principles of dataflow design at different layers of abstraction. The development processes integrated in our approach are software implementation, hardware implementation, hardware-software co-design, and optimized application mapping. The proposed methodology facilitates development and integration of signal processing hardware and software modules that involve heterogeneous programming languages and platforms. As a demonstration of the proposed design framework, we present a dataflow-based deep neural network (DNN) implementation for vehicle classification that is streamlined for real-time operation on embedded SoC devices. Using the proposed methodology, we apply and integrate a variety of dataflow graph optimizations that are important for efficient mapping of the DNN system into a resource constrained implementation that involves cooperating multicore CPUs and field-programmable gate array subsystems. Through experiments, we demonstrate the flexibility and effectiveness with which different design transformations can be applied and integrated across multiple scales of the targeted computing system.
AB - This paper presents a new methodology for design and implementation of signal processing systems on system-on-chip (SoC) platforms. The methodology is centered on the use of lightweight application programming interfaces for applying principles of dataflow design at different layers of abstraction. The development processes integrated in our approach are software implementation, hardware implementation, hardware-software co-design, and optimized application mapping. The proposed methodology facilitates development and integration of signal processing hardware and software modules that involve heterogeneous programming languages and platforms. As a demonstration of the proposed design framework, we present a dataflow-based deep neural network (DNN) implementation for vehicle classification that is streamlined for real-time operation on embedded SoC devices. Using the proposed methodology, we apply and integrate a variety of dataflow graph optimizations that are important for efficient mapping of the DNN system into a resource constrained implementation that involves cooperating multicore CPUs and field-programmable gate array subsystems. Through experiments, we demonstrate the flexibility and effectiveness with which different design transformations can be applied and integrated across multiple scales of the targeted computing system.
KW - 113 Computer and information sciences
U2 - 10.1016/j.sysarc.2018.12.010
DO - 10.1016/j.sysarc.2018.12.010
M3 - Article
VL - 93
SP - 1
EP - 19
JO - Journal of Systems Architecture
JF - Journal of Systems Architecture
SN - 1383-7621
ER -